AI Shopping Assistant - Built using LangGraph

In this video, I present a detailed overview of our AI Shopping Assistant solution to the high-friction retail in-store shopping experience. We'll explore common issues like poor customer service, difficulty finding items, and a lack of effective pre-purchase marketing.
Our innovative solution involves a Chat based AI assistant designed to help customers find items, explain product details, and upsell relevant products. I'll take you through our journey from problem identification to the development of a Minimum Viable Product (MVP) built with OpenAI GPT-4 and a vector-based self-querying retriever for accurate product recommendations. This is all bought together by leveraging LangGraph agents.
If you're interested in AI, retail technology, or simply curious about how advanced chat agents can transform the shopping experience, this video is for you. Follow along as I learn more about leveraging the latest and greatest tools in AI! If you are interested in custom solutions for your business please reach out to me directly.
Keywords: AI Shopping Assistant, retail tech, in-store experience, SMS-based assistant, OpenAI GPT-4, product recommendation, AI demo, LangChain, LangGraph, retail innovation, How to build an AI Shopping Assistant, AI customer service, AI product recommendations, building AI for retail, retail AI solutions, AI chatbot for shopping, AI in retail, creating an AI assistant, AI-powered shopping experience, AI technology for stores, Business AI Implementation
#ai #chatgpt #aisolutions #sales #datascience #softwareengineer #langchain

[@HerroEverynyan]

This is fabulous. And the way you explain is so refreshing and easy to follow.

[@levbszabo]

@@HerroEverynyan thank you! I appreciate it - this comment inspired me to make more videos 😂

[@yiannisstamoulis]

very nice thanks

[@levbszabo]

Most welcome

[@awakenwithoutcoffee]

pretty cool, we are working/learning on something similar and its good to see were on the right track but LangGraph is a tough nut to crack so far. Any pointers in learning more about meta-data creation/filtering ? Best of luck with your business brother.

[@levbszabo]

Thanks! Out of curiosity, what is your use case?

[@awakenwithoutcoffee]

@@levbszabo Multiple: as part of our start-up we are working on several projects that could benefit from a LangGraph back-end. Our first project is an innovative RAG based solution for enterprises while our second project focuses on e-commerce. The e-commerce market is massive and something we researched extensively over the years. We already build several MVP's using low-code platforms but decided to dive deep and do it from scratch which is fun but difficult. Were recording the whole process and hope to be inspiring others to follow their ambitions.

[@levbszabo]

Seeing your follow up question now - this is what I used in this example python.langchain.com/v0.1/docs/modules/data_connection/retrievers/self_query/ if you are missing the meta-data, then there are unsupervised learning methods you can use to pre process. I've set up a free community where I am happy to share resources + answer questions if you are interested course.journeymanai.io/ best of luck!

[@awakenwithoutcoffee]

@@levbszabo appreciate the reply. I signed up for your community and really like your course outline (sadly not able to afford it right now but it looks well structured).
Out of curiosity can you talk a bit more about unsupervised learning for meta-data creation ? that's new to me.

[@levbszabo]

@@awakenwithoutcoffee I appreciate it! I’ll be posting some sub modules for free on here as they become available. Some unsupervised tools you could use **LDA** identifies topics from text data, outputting themes that can be used as metadata. **K-Means** clusters feature vectors (we could map the product descriptions to a vector using openai vector models (first) , grouping similar items to assign metadata like categories.

[@polo15s60]

hey, can you please provide the link for the kaggle dataset if possible))

[@judsonrobertson]

This is great !

[@AjayCoding]

how can we integrate this app into different web solutions like webflow, framer, Wordpress, and react,etc...????

[@abderahimmazouz2088]

Hey , thank you for the explanation, wouldn't be better if we use other tools such as PythonREPL to exctract information from this csv file / dataframe ?

[@levbszabo]

Hey, my hesitation with PythonREPL is that it is much less deterministic and has a tendency to error out. But a tool that can 'slice/dice' the dataframe is definitely useful

[@puneetsatyendrasi]

Hey
Is it okay to have some source code now?

[@andy111007]

Thanks for the explanation and video. is code available?

[@levbszabo]

I’ll try to make future projects public, this one is still work in progress. If you need any help with langgraph stuff though just shoot me a message

[@divyanshtripathi4867]

This was great! Can you share the source code?

[@levbszabo]

Thank you! I didn’t make this code public since we are still building parts of it for a client - I’ll try to make all future projects accessible!

[@AbdulW.Official]

Code

[@maysammansor]

Without sharing the code your teaching career wouldn't go that far

[@YeahTheBros]

😢

[@stigsfoot]

Cool. Insta-sub. Would love to collab

[@levbszabo]

Thanks, I like your channel too. Send me an email - I'm happy to chat course.journeymanai.io/contact